ACE Step 1.5

ACE Step 1.5 is an ultra-affordable AI music generation model that creates songs from style tags and lyrics. With support for up to 4-minute tracks and flexible duration control, it delivers quality music at an extremely low cost.

Why Choose This?

Ultra-low cost Generate music at a fraction of a cent per second.
Long-form generation Create tracks up to 240 seconds (4 minutes) in length.
Flexible duration Precise control over output length with a slider.
Tag-based styling Use comma-separated tags to define genre, instruments, and mood.
Structured lyrics Support for [Verse], [Chorus], [Bridge] and other section markers.

Parameters

Parameter	Required	Description
tags	Yes	Style tags: genre, instruments, mood (comma-separated)
lyrics	No	Song lyrics with structure markers
duration	No	Track length in seconds (up to 240, default: 60)
seed	No	Random seed for reproducibility (-1 for random)

Tags Format

Use comma-separated values to describe the musical style:

Examples:

steampunk, electro swing, jazz, piano, ticking clock

pop, female vocals, upbeat, guitar, 120bpm

lo-fi, chill, ambient, piano, rainy mood

Lyrics Format

Use structure markers in brackets to guide song arrangement:

[Verse] Ticking tocking goes the clock Turning keys and pick the lock Steam is rising, gears go round Listen to that brassy sound

[Chorus] Round and round we go today In this smoky cabaret Fix the future, fix the past

How to Use

Enter your tags — describe the musical style with comma-separated tags.
Write your lyrics (optional) — add structured lyrics with section markers.
Set duration — choose track length up to 240 seconds.
Set seed (optional) — use a specific seed for reproducible results.
Run — submit and download your generated music.

Pricing

Duration	Cost
Per second	$0.0003

Best Use Cases

Background Music — Generate affordable background tracks for videos and content.
Demo Production — Quickly prototype song ideas at minimal cost.
Bulk Generation — Produce large volumes of music cost-effectively.
Content Creation — Custom music for social media, podcasts, and games.
Experimentation — Explore styles and ideas without worrying about cost.

Pro Tips

Combine multiple style tags for more specific results.
Use structure markers in lyrics for well-arranged songs.
Generate longer tracks (240s) for full-length background music.
Leave lyrics empty for instrumental-only tracks.
Use the same seed to reproduce identical results.
Experiment freely — each minute costs less than $0.02.

Notes

Tags is the only required field.
Maximum track duration is 240 seconds (4 minutes).
Without lyrics, the model generates instrumental music.
Seed value -1 generates a random seed each time.

Related Models

HeartMuLa Generate Music — Generate songs with multilingual lyrics support.
ElevenLabs Music — Premium music generation with multiple output formats.

Ace Step 1.5 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step-1.5 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Ace Step 1.5 below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step-1.5" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "duration": 60,
    "seed": -1
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/ace-step-1.5", {
        "duration": 60,
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/ace-step-1.5",
    {
    "duration": 60,
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Ace Step 1.5 API — Frequently asked questions

What is the Ace Step 1.5 API?

Ace Step 1.5 is a WaveSpeedAI model for audio generation, exposed as a REST API on WaveSpeedAI. ACE-Step 1.5 generates up to 4-minute music with lyrics from text. Supports 50+ languages, high acoustic fidelity, and runs efficiently on consumer hardware. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Ace Step 1.5 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ace-step-1.5.

How much does Ace Step 1.5 cost per run?

Ace Step 1.5 starts at $0.000 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Ace Step 1.5 accept?

Key inputs: `duration`, `seed`, `lyrics`, `tags`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ace-step-1.5.

How long does Ace Step 1.5 take to generate?

Average end-to-end generation time on WaveSpeedAI is around 11 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Ace Step 1.5 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README

ACE Step 1.5

Why Choose This?

Parameters

Tags Format

Lyrics Format

How to Use

Pricing

Best Use Cases

Pro Tips

Notes

Related Models

Ace Step 1.5 API — Quick start

Ace Step 1.5 API — Frequently asked questions